SMRTR AIApr 30, 2026John D. Cook

Three ways to differentiate ReLU

SMRTR summary

ReLU (max(0, x)) isn't differentiable at x = 0, but three approaches handle this: pointwise (Heaviside), distributional derivatives, and the subgradient, which allows any slope between 0 and 1 at that point.

SMRTR provides this summary for quick context. The original article belongs to John D. Cook.

Read the original article
SMRTR AI

Get the next batch of curated summaries in your inbox.

This archive is built from SMRTR newsletter summaries. Subscribe for hand-picked stories without the extra noise.